All posts

Posts tagged with Optimization

Adadelta

Reducing the aggresive learning rate decay in Adagrad

Adagrad

Parameter updates with unique learning rate for each parameter

Adam

RMSprop with momentum

Adamax

Adamax description

Batch Gradient Descent

Minimizing cost functions with a subset of the dataset

Nadam

Adam with Nesterov momentum

RMSprop

Reducing the aggresive learning rate decay in Adagrad using the twin sibling of Adadelta

Stochastic Gradient Descent

Minimizing cost functions with a random data point at a time